{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,2,21]],"date-time":"2025-02-21T01:11:23Z","timestamp":1740100283174,"version":"3.37.3"},"reference-count":22,"publisher":"IEEE","license":[{"start":{"date-parts":[[2021,5,30]],"date-time":"2021-05-30T00:00:00Z","timestamp":1622332800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2021,5,30]],"date-time":"2021-05-30T00:00:00Z","timestamp":1622332800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,5,30]],"date-time":"2021-05-30T00:00:00Z","timestamp":1622332800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100000266","name":"Engineering and Physical Sciences Research Council","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100000266","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100006041","name":"Innovate UK","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100006041","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2021,5,30]]},"DOI":"10.1109\/icra48506.2021.9561545","type":"proceedings-article","created":{"date-parts":[[2021,10,20]],"date-time":"2021-10-20T00:28:35Z","timestamp":1634689715000},"page":"5959-5965","source":"Crossref","is-referenced-by-count":1,"title":["Robot in a China Shop: Using Reinforcement Learning for Location-Specific Navigation Behaviour"],"prefix":"10.1109","author":[{"given":"Bian","family":"Xihan","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Oscar","family":"Mendez","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Simon","family":"Hadfield","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"article-title":"Ai2-thor: An interactive 3d environment for visual ai","year":"2017","author":"kolve","key":"ref10"},{"key":"ref11","article-title":"Hierarchical deep reinforcement learning: Integrating temporal abstraction and intrinsic motivation","author":"kulkarni","year":"2016","journal-title":"Neural Information Processing Systems(NIPS)"},{"article-title":"A model-based approach for sample-efficient multi-task reinforcement learning","year":"2019","author":"landolfi","key":"ref12"},{"key":"ref13","first-page":"121","article-title":"An iterative image registration technique with an application to stereo vision","author":"lucas","year":"1981","journal-title":"Imaging Understanding Workshop"},{"key":"ref14","first-page":"1928","article-title":"Asynchronous methods for deep reinforcement learning","author":"mnih","year":"2016","journal-title":"International Conference on Machine Learning"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1038\/nature14236"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/PROC.1983.12684"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2004.1315094"},{"article-title":"Progressive neural networks","year":"2016","author":"rusu","key":"ref18"},{"key":"ref19","first-page":"1889","article-title":"Trust region policy optimization","author":"schulman","year":"2015","journal-title":"International Conference on Machine Learning"},{"key":"ref4","first-page":"134","article-title":"Attentive multi-task deep reinforcement learning","author":"br\u00e4m","year":"2019","journal-title":"Proceedings of the European Conference on Machine Learning and Knowledge Discovery in Databases"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2017.8206050"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1016\/0004-3702(81)90024-2"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.1997.649076"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.336"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/JRA.1987.1087143"},{"key":"ref2","first-page":"507","article-title":"Agent57: Outperforming the atari human benchmark","author":"badia","year":"2020","journal-title":"International Conference on Machine Learning"},{"key":"ref1","article-title":"Hindsight experience replay","author":"andrychowicz","year":"2017","journal-title":"Neural Information Processing Systems(NIPS)"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICCE.2018.8326229"},{"article-title":"Proximal policy optimization algorithms","year":"2017","author":"schulman","key":"ref20"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2017.7989381"},{"key":"ref21","article-title":"Distral: Robust multitask reinforcement learning","author":"teh","year":"2017","journal-title":"Neural Information Processing Systems(NIPS)"}],"event":{"name":"2021 IEEE International Conference on Robotics and Automation (ICRA)","start":{"date-parts":[[2021,5,30]]},"location":"Xi'an, China","end":{"date-parts":[[2021,6,5]]}},"container-title":["2021 IEEE International Conference on Robotics and Automation (ICRA)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9560720\/9560666\/09561545.pdf?arnumber=9561545","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,5,10]],"date-time":"2022-05-10T15:47:12Z","timestamp":1652197632000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9561545\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,5,30]]},"references-count":22,"URL":"https:\/\/doi.org\/10.1109\/icra48506.2021.9561545","relation":{},"subject":[],"published":{"date-parts":[[2021,5,30]]}}}